INDEX

Explanations

phrases indicating the consequences or implications of a particular situation

oai_token-act-pair · gpt-3.5-turbo

the repeated phrase "the fact that."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.9.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aukee

-0.74

vc

-0.74

uttering

-0.70

yna

-0.68

-0.66

pec

-0.64

Si

-0.64

gur

-0.64

think

-0.64

TPPStreamerBot

-0.63

POSITIVE LOGITS

 they

1.04

 someone

0.91

we

0.90

 humans

0.90

 there

0.85

 nobody

0.85

 everyone

0.81

he

0.81

 these

0.80

 somebody

0.78

Activations Density 0.109%

phrases indicating the consequences or implications of a particular situation

the repeated phrase "the fact that."

No Comments

No Known Activations